Publications (5)
Probing the Transition to Dataset-Level Privacy in ML Models Using an Output-Specific and Data-Resolved Privacy Profile
Tyler LeBlond, Joseph Munoz, Fred Lu +4
Differential privacy (DP) is the prevailing technique for protecting user data in machine learning models. However, deficits to this framework include a lack of clarity for selecti…
Only My Model On My Data: A Privacy Preserving Approach Protecting one Model and Deceiving Unauthorized Black-Box Models
Weiheng Chai, Brian Testa, Huantao Ren +2
Deep neural networks are extensively applied to real-world tasks, such as face recognition and medical image classification, where privacy and data protection are critical. Image d…
Privacy against Real-Time Speech Emotion Detection via Acoustic Adversarial Evasion of Machine Learning
Brian Testa, Yi Xiao, Harshit Sharma +2
Smart speaker voice assistants (VAs) such as Amazon Echo and Google Home have been widely adopted due to their seamless integration with smart home devices and the Internet of Thin…
A General Framework for Auditing Differentially Private Machine Learning
Fred Lu, Joseph Munoz, Maya Fuchs +5
We present a framework to statistically audit the privacy guarantee conferred by a differentially private machine learner in practice. While previous works have taken steps toward…
Sparse Private LASSO Logistic Regression
Amol Khanna, Fred Lu, Edward Raff +1
LASSO regularized logistic regression is particularly useful for its built-in feature selection, allowing coefficients to be removed from deployment and producing sparse solutions.…